Towards a holistic approach for AI trustworthiness assessment based upon aids for multi-criteria aggregation - IRT SystemX Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Towards a holistic approach for AI trustworthiness assessment based upon aids for multi-criteria aggregation

Henri Sohier
  • Fonction : Auteur
  • PersonId : 1054948
Kahina Amokrane
Afef Awadid
  • Fonction : Auteur
  • PersonId : 1048939
Souhaiel Khalfaoui
  • Fonction : Auteur
  • PersonId : 768857
  • IdRef : 169958590

Résumé

The assessment of AI-based systems trustworthiness is a challenging process given the complexity of the subject which involves qualitative and quantifiable concepts, a wide heterogeneity and granularity of attributes, and in some cases even the non-commensurability of the latter. Evaluating trustworthiness of AI-enabled systems is in particular decisive in safety-critical domains where AIs are expected to mostly operate autonomously. To overcome these issues, the Confiance.ai program [1] proposes an innovative solution based upon a multi-criteria decision analysis. The approach encompasses several phases: structuring trustworthiness as a set of well-defined attributes, the exploration of attributes to determine related performance metrics (or indicators), the selection of assessment methods or control points, and structuring a multi-criteria aggregation method to estimate a global evaluation of trust. The approach is illustrated by applying some performance metrics to a data-driven AI context whereas the focus on aggregation methods is left as a near-term perspective of Confiance.ai milestones.
Fichier principal
Vignette du fichier
15.pdf (2.07 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
licence : CC BY - Paternité

Dates et versions

hal-04086455 , version 1 (02-05-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04086455 , version 1

Citer

Juliette Mattioli, Henri Sohier, Agnès Delaborde, Gabriel Pedroza, Kahina Amokrane, et al.. Towards a holistic approach for AI trustworthiness assessment based upon aids for multi-criteria aggregation. SafeAI 2023 - The AAAI's Workshop on Artificial Intelligence Safety, AAAI, Feb 2023, Washington, D.C., United States. ⟨hal-04086455⟩
97 Consultations
69 Téléchargements

Partager

Gmail Facebook X LinkedIn More